Muse Wonder Full: benchmark results
Meta's higher-capability Muse Wonder Full (October 12, 2026), available through paid Muse Code subscriptions with a one-million-token context. The publisher does not offer a public checkpoint download. Provider: Meta. Released 2026-10-12. Access: Interface.
Aggregate Rating 1916 ± 12, rank #17 of 10318 rated models, from 172 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Coding Agent Index v2.0 - SWE-Atlas-QnA-AA | 68.82 | Task Resolve Rate (%) | 100 |
| AA Coding Agent Index v2.1 - SWE-Atlas-QnA-AA | 68.82 | Task Resolve Rate (%) | 100 |
| AutomationBench-AA - HR - Raw Objective Completion | 83.32 | Raw Objective Completion (%) | 100 |
| Harvey LAB-AA | 13.06 | Hallucination-Gated All-Pass Rate (%) | 100 |
| Harvey LAB-AA - Corporate M&A | 98.18 | Criterion Pass Rate (%) | 100 |
| Harvey LAB-AA - Funds & Asset Management | 95.72 | Criterion Pass Rate (%) | 100 |
| Harvey LAB-AA - International Trade & Sanctions | 96.41 | Criterion Pass Rate (%) | 100 |
| Harvey LAB-AA - Real Estate | 98.06 | Criterion Pass Rate (%) | 100 |
| Harvey LAB-AA - White Collar Defense & Investigations | 95.74 | Criterion Pass Rate (%) | 100 |
| LLM Stats (DeepSWE 1.1) | 79 | Score (%) | 100 |
| LLM Stats (JobBench) | 75.3 | Score (%) | 100 |
| LLM Stats (Personal Superintelligence Index) | 59.1 | Score (%) | 100 |
Interactive version: theaggregate.ai/model?slug=muse-wonder-full · How It Works · Data refreshed daily, snapshot 2026-11-14.